非线性连续神经网络平衡态的吸引域及收敛指数的估计
THE ESTIMATES OF CONVERGENT RATE AND ATTRACTIVE DOMAIN OF NONLINEAR CONTINUOUS NEURAL NETWORK
-
摘要: 给出一种新的简单方法分析非线性连续神经网络的指数稳定性。得到了最优化计算神经网络全局指数稳定的一些判定条件,以及联想记忆神经网络各平衡态的吸引域与收敛速度估计。所得结论推广了某些文献中已有结果。Abstract: The estimates of attractive domain and convergent rate of nonlinear continuous memory neural network are obtained, and some sufficient conditions for the network to be globally exponentially stable are developed, these results generalize ones in references.
-
Killy D G. Stability in contractive nonlinear neural networks. IEEE Trans. on Biomedical Engineering, 1990, BME-37: 231-242.[2]Sugawara K, Harao M. On the stability of equilibrium states of analogue neural networks. Trans-[3]actions of the Institute of Electronics and Communication Engineers, 1983, J-66-A: 258-265.[4]Subhrsanan S I, Sundareshan M K. Exponential stability and a systematic synthesis of a neural network for quadratic minimization[J].Neural Networks.1991, 4:599-613[5]Bouzerdoum A, Pattison T R. Neural network for quadratic optimization with bound constraints. IEEE Trans. on Neural Networks, 1993, NN-4: 293-303.[6]Avitabile G, Forti M, et al. On a class of nonsymmetrical neural networks with application to ADC. IEEE Trans. on Circuits and Syst, 1991, CAS-38(2): 202-208.[7]Bauer F, Stoer J, Witzgall C. Absolute and monotonic norms[J].Numer. Math.1961, 3:257-264 -
计量
- 文章访问数: 2028
- HTML全文浏览量: 127
- PDF下载量: 552
- 被引次数: 0